AI & ML
RecallFlow: Episodic Memory as the Source Distribution of Generative Robot Policies
arXiv cs.RO0 views
arXiv:2611.23731v1 Announce Type: new Abstract: Diffusion and flow-matching policies have become a standard choice for visuomotor imitation learning, owing to their ability to model multimodal action distributions. In memory-dependent manipulation, the robot must act on information that is no longer visible. Existing methods feed the observation history to the policy as an additional condition, while action generation still starts from Gaussian noise. However, the policy must then pick out the relevant target from a long and redundant history, leading to spurious correlations and unreliable decisions as the memory load grows. Additionally, the initial noise carries no information about what the robot has seen, leaving generation without guidance toward the remembered target. To address these issues, we propose RecallFlow, a flow-policy framework that builds the source distribution from episodic memory. Recall-Relocalization relates the memory to the current view through a few recall slots, so that the source reflects where the remembered targets are now. Recall Anchors then turns each slot into a Gaussian component of the source, enabling generation to start close to the intended action instead of from noise. The transport network then completes the action from the current observation alone, keeping inference nearly as cheap as a memoryless policy. We further build a suite of memory-dependent tasks grouped by memory load and compare all policies under a matched protocol. Extensive experiments show that RecallFlow achieves a state-of-the-art average success rate of 80.4% on the public MIKASA-Robo memory benchmark, and outperforms the strongest baseline by 20.3 points on our suite and by 18.8 points on four real-robot tasks.
Source:https://arxiv.org/abs/2611.23731PreviousImproving While Deployed: Learning Proactive End-to-End Driving from Imperfect Human Takeover DataNextZERITH V2.5: From Predictive Power to Policy Learnability
Related posts
ASDL: A Fast Vector Approximation Algorithm for Multiplierless Designs of Convolutional Neural Networks
0arXiv eess.SP
Multi-Modal Environment-Aware Beam Management for Massive MIMO: A Geometry-Driven Virtual Base Station Framework
0arXiv eess.SP
TinyMyo: a Tiny Foundation Model for Flexible EMG Signal Processing at the Edge
0arXiv eess.SP
Chirp-Permuted AFDM: A Versatile and Multifunctional Waveform for 6G
0arXiv eess.SP
Synthesizing hyperspectral Data using generative Models to train spectral Unmixing Methods for low-cost Crop Residue Cover Mapping
0arXiv eess.SP
From Points to Trajectories: Rethinking Multimodal Alignment for Physical Events
0arXiv eess.SP